Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 16144
    Prev
    Next
    INDEX
    Explanations

    references to plot elements or discussions about the plot in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Unmount
    -0.62
     antigu
    -0.61
     bianchi
    -0.58
    ReusableCell
    -0.56
    CompilerServices
    -0.56
    довлет
    -0.56
    ماذا
    -0.56
     /\.(
    -0.55
    関連項目
    -0.55
    льтра
    -0.55
    POSITIVE LOGITS
     plot
    3.29
     plots
    3.11
     Plot
    3.03
     PLOT
    3.02
    plot
    2.99
     Plots
    2.94
    Plot
    2.86
    plots
    2.64
    PLOT
    2.64
    Plots
    2.46
    Activations Density 0.041%

    No Known Activations